Hybrid Learning Algorithm Based Modified Particle Swarm Clustering for RBF Neural Network

2015 ◽  
Author(s):  
Ying Guo ◽  
Hongtao Wang
Keyword(s):  
Neural Network ◽  
Learning Algorithm ◽  
Rbf Neural Network ◽  
Particle Swarm ◽  
Hybrid Learning ◽  
Hybrid Learning Algorithm

Fuzzy Neural Network Hybrid Learning Control on AUV

2012 ◽  
Vol 468-471 ◽  
pp. 1732-1735
Author(s):  
Jing Zhao ◽  
Zhao Lin Han ◽  
Yuan Yuan Fang
Keyword(s):  
Neural Network ◽  
Fuzzy Neural Network ◽  
Autonomous Underwater Vehicle ◽  
Learning Algorithm ◽  
Hybrid Learning ◽  
Network Control ◽  
Learning Ability ◽  
B Spline ◽  
Hybrid Learning Algorithm ◽  
Fuzzy Neural

A novel controller based on the fuzzy B-spline neural network is presented, which combines the advantages of qualitative defining capability of fuzzy logic, quantitative learning ability of neural networks and excellent local controlling ability of B-spline basis functions, which are being used as fuzzy functions. A hybrid learning algorithm of the controller is proposed as well. The results show that it is feasible to design the fuzzy neural network control of autonomous underwater vehicle by the hybrid learning algorithm.

AN Improved RBF Neural Network Model Based on Hybrid Learning Algorithm

2013 ◽  
Vol 718-720 ◽  
pp. 2202-2207
Author(s):  
Zhao Hu Deng ◽  
Yan Qin Zhang
Keyword(s):  
Neural Network ◽  
Traditional Method ◽  
Learning Algorithm ◽  
Rbf Neural Network ◽  
Clustering Algorithms ◽  
Hybrid Learning ◽  
Descent Method ◽  
Learning Ability ◽  
Steepest Descent Method ◽  
Training Samples

When building the radial basis function (RBF) neural network with traditional method, the property of the network is easily influenced by the distribution of training samples. The learning ability and generalization ability are hard to achieve the optimum. In this paper, it presents a new method to solve this problem. In the method it replaced the traditional clustering algorithms with genetic algorithms to optimize the distribution of RBF. At the same time it combined the steepest descent method with GA to solve the binary defect of GA encoding. After experiments the results showed that the constructed neural network has a better architecture and more accuracy than that built with traditional method.

Sign in / Sign up

Export Citation Format

Share Document